create_draft

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Without any annotations, the description provides critical behavioral limits, including the 25 MB limit for attachments and specific requirements for attachment locations (local paths or designated roots). It clarifies the state of the generated object (a draft, not a sent message).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The information is highly functional and well-organized, front-loading the most important constraint (it is not sent). It is slightly dense due to the multitude of rules but maintains high information density.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity—involving message threading logic, content formatting rules, and strict file system/size constraints—the description is exceptionally complete. It covers all major functional edge cases for this tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description is highly vital. It clarifies that `reply_to_message_id` requires an empty subject, and `attachments` requires local paths and adheres to a size constraint. This compensation for lack of schema detail is excellent.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly defines the action (Create a draft) and the crucial behavioral constraint that it is not a sending action, clearly distinguishing it from siblings like 'send' or 'update_draft'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides explicit guidance on using reply_to_message_id for threading, specifically instructing the agent to leave the subject empty to achieve the correct 'Re:' formatting. This is a specific behavioral prerequisite for correct usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.